Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full burden. It usefully discloses that results are deterministic and that npm registry abbreviated metadata is the source, plus what categories are checked, but says nothing about network behavior, failure modes, or what an incompatible result looks like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single tightly packed sentence that front-loads the verb and the three check categories, with the metadata source as a trailing qualifier. No padding or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

It enumerates the checks performed, which is the key information for a validation tool, and there is no output schema requiring explanation. Minor gap: it does not hint at the shape of the verdict (per-dependency results vs. a single pass/fail).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: each of the three parameters is documented in the schema, including the behavior when runtime_version is omitted. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ("Verifies") and precisely enumerates the resources checked: engines.node, peerDependencies cross-compatibility, and deprecation notices. This clearly separates it from siblings like detect_project_environment or get_upgrade_steps, though it never names an alternative explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or when-not-to-use statement, and no sibling is named. The scope (compatibility verification against npm metadata) implies the pre-upgrade/validation scenario, but the agent must infer it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden; it usefully discloses that detection is local and network-free, which is real behavioral value. However it omits failure/error behavior (e.g. missing package.json), whether it is strictly read-only, and any output shape, leaving notable gaps for an unannotated tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence opens with the verb and then enumerates the detectable items. The parenthetical lists are dense but each item is informative, so nearly every token earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool with no output schema, the description enumerates what will be detected, which effectively conveys the return content. It is nearly complete, missing only error conditions and confirmation that the operation is non-mutating.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is a single parameter at 100% schema description coverage, so the schema already documents project_path fully. The description adds only the loose notion of 'local project files' and no syntax or format detail beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Detects') and enumerates the exact resources: Node.js runtime, package manager, locked dependency versions, and specific config paradigms. The read-only, local-only framing ('from local project files') clearly separates it from the sibling tools, which concern compatibility checking, setup guides, and upgrade steps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'from local project files without network calls' implies a first-step, offline detection context, but the description never states when to reach for this tool versus siblings like check_dependency_compatibility or get_upgrade_steps. Usage is inferable but not explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the full burden. It does disclose the nature of the output (guides, breaking changes, codemod commands, GitHub tag source URLs), which is useful, but says nothing about read-only safety, authentication, rate limits, or result size/pagination.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One densely packed sentence that front-loads the core capability and then illustrates it with concrete version-pair examples. No filler, though the trailing parenthetical is long enough that it could be split for readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully enumerates what comes back (migration steps, breaking changes, codemod commands, source URLs). The 5-parameter surface is fully covered by the schema, and no annotations exist to contradict. Only the absence of any guidance on result size or failure modes keeps it from a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all five parameters including focus_area and package_manager are fully documented in the schema. The description adds no syntax or format guidance beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb ('Retrieves') plus concrete resource ('step-by-step migration guides, breaking changes, and official codemod commands between two versions'), with real-world examples (Tailwind v3->v4, ESLint v8->v9). It implicitly separates itself from search_versioned_docs and get_versioned_setup_guide by scoping to a version-to-version upgrade, though it never names a sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the 'between two versions' framing, so an agent can infer this is the tool for upgrade planning. However there is no explicit when-to-use, when-not-to-use, or routing against the sibling tools (e.g. check_dependency_compatibility vs this one).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It does usefully disclose the output shape (citation-backed commands, config examples, obsolete patterns), which implies a read-only retrieval operation, but it says nothing about permissions, rate limits, determinism, or whether results are cached/stale. Adequate but incomplete for an unannotated tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence listing the three returned artifacts (commands, config examples, obsolete patterns), with zero filler. It is dense but every clause maps to real output content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only retrieval tool with fully documented parameters and no output schema, the description conveys the substance of what comes back. The main gap is routing versus siblings like get_upgrade_steps, but the core call decision is covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all five parameters including enums and the 'do NOT pass latest' warning. The description only adds that commands are formatted for the project's package manager and scoped to a specific version, which lightly reinforces package_manager and target_version but adds little beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb-and-resource pair — returns installation commands, config file examples, and obsolete patterns for a specific library version — which is far more concrete than the tool name alone. It implicitly separates itself from check_dependency_compatibility and search_versioned_docs by being a setup-oriented, version-pinned guide, though it never names a sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives such as get_upgrade_steps or search_versioned_docs. The agent must infer from the name and description that this is the setup path rather than the upgrade or general-docs path.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It usefully discloses the retrieval engine (FTS5/BM25) and the lockfile-based version fallback, but says nothing about result ranking, chunk format, or any limits beyond the search mechanism itself.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences that front-load the purpose and then the version-resolution behavior. Every clause earns its place with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter search tool with no annotations and no output schema, the description adequately covers purpose and the version fallback, but omits what a result looks like and how ranking/filtering behaves. It is workable but leaves gaps an agent might want covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all six parameters thoroughly. The description restates the version-resolution fallback but adds no syntax or format detail beyond the schema, making the baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (searches) and a well-scoped resource (tag-pinned migration guides, release notes, deprecation notices for a specific library version). It clarifies its retrieval mechanism (SQLite FTS5/BM25), but does not explicitly distinguish itself from siblings like get_versioned_setup_guide or get_upgrade_steps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the resource description (find version-specific migration information), and the version-resolution fallback is noted, but there is no explicit when-to-use-this-vs-alternatives guidance naming the sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.